Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2853 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1593940 (Python Code)

Max Activating Token Index: 25

Text #1

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3704. Min Act: -0.0000

Data Index: 837390 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1398201 (Python Code)

Max Activating Token Index: 769

Text #3

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1638141 (Python Code)

Max Activating Token Index: 278

Text #4

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1524158 (Python Code)

Max Activating Token Index: 24

Text #5

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1463534 (Python Code)

Max Activating Token Index: 450

Text #6

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3023. Min Act: -0.0000

Data Index: 653477 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.2913. Min Act: -0.0000

Data Index: 886478 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1416014 (Python Code)

Max Activating Token Index: 165

Text #9

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3093. Min Act: -0.0000

Data Index: 75608 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3082. Min Act: -0.0000

Data Index: 205821 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1367327 (Python Code)

Max Activating Token Index: 798

Text #12

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1041910 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1574707 (Python Code)

Max Activating Token Index: 35

Text #14

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.2800. Min Act: -0.0000

Data Index: 330989 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1373650 (Python Code)

Max Activating Token Index: 924

Text #16

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1474217 (Python Code)

Max Activating Token Index: 197

Text #17

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.2799. Min Act: -0.0000

Data Index: 1287334 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1486459 (Python Code)

Max Activating Token Index: 417

Text #19

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.2839. Min Act: -0.0000

Data Index: 922743 (C4 (Web Text))

Max Activating Token Index: 571